Harvard physicist Matthew Schwartz releases BootLoops, an open-source harness that let Claude produce 36 manuscripts in 18 fields in three months
Event confirmedAwaiting review
The takeaway
On Oct 1, 2026 Anthropic published a guest post, “Claude-Shaped Science”, by Harvard theoretical physicist Matthew Schwartz (a visiting researcher at Anthropic).
Status
- Claim
Event confirmedAwaiting review
- Our reporting
- High confidence
- Verification
- Preprint only
- Importance
- 3 of 5
- Last verified
- 29 October 2026
Your AI and this story
- GPT-6.2 Astra123 days after its cutoff
- Claude Opus 5.593 days after its cutoff
- Gemini 4 Hydrogen184 days after its cutoff
- Grok 4.7123 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 93 days before it.
Key facts
- Second wave (Science, 22 Oct 2026): news feature by Celina Zhao, ‘Across fields, AI finds solutions hiding in plain sight’, subtitle: ‘“BootLoops” software enabled researchers to quickly find and attack problems in 22 disciplines’ (doi 10.1126/science.aen4281; full text paywalled, read from the abstract only)
- Output: 36 manuscripts in 18 fields with 19 co-authors over about three months, picked from ~400 candidate problems (Anthropic guest post)
- Particle physics: 30 integrals computed with the bootstrap method, 15 reproducing known results and 15 never computed before
- Economics (NBER w35782, Schwartz, Isaiah Andrews, Jesse M. Shapiro): the workflow ran 4,452 replication packages from five journals, flagged discrepancies in 3,460 articles or appendices, cut computation time >10x in 496, and proposed extensions in 923
- Other projects: population genetics on 5.7 billion mutation pairs from the 1000 Genomes Project; a word-stress database (AccStack) covering 6,072 languages; every US forest-inventory plot classified by life-history strategy
- BootLoops is owned and maintained by Schwartz; the work was funded by Anthropic but it is ‘not an Anthropic project’ (bootloops.ai)
- Caveats from Schwartz: Claude ‘likes to declare victory too early’, and ‘done, with one asterisk’ often means ‘not done at all’; first findings were often ‘technically correct but scientifically unremarkable’ until domain experts steered them
- Science news (Celina Zhao, 22 Oct issue), ‘Across fields, AI finds solutions hiding in plain sight’: ‘“BootLoops” software enabled researchers to quickly find and attack problems in 22 disciplines’ (standfirst; full text paywalled, read from the Crossref record)
What happened
Schwartz argues there is an “impedance mismatch” between how scientists work and what LLMs do best, so instead of making Claude imitate a scientist he looked for “Claude-shaped problems”: exact, checkable calculations that recur across fields. BootLoops packages the tools and loops for such work. He reports that Claude reproduced one paper’s results in about twenty minutes, a calculation that took him weeks to code originally.
Why it matters
It is one of the broadest demonstrations so far of a single researcher using an AI agent to work across many unrelated fields, with code released openly. The economics replication alone (thousands of papers re-run, thousands of discrepancies flagged) could matter for research transparency. Schwartz’s warnings about premature “victory” are a useful counterweight to autonomous-science claims.
What is disputed or not yet verified
| Verification | Preprints and working papers; expert co-authors; NBER working paper (not peer-reviewed) |
|---|
Sources
7 sources from 6 sites. Numbers match the chips in the text.
7 sources: 4 primary, 3 press
Primary
- Anthropic (guest post by Matthew Schwartz): Claude-Shaped Scienceanthropic.com, official
- BootLoops: a toolkit for exact quantitative sciencebootloops.ai, official
- BootLoops source code (GitHub)github.com, code
- NBER w35782: An LLM Workflow That Reproduces, Improves, and Extends Published Economics Research (Schwartz, Andrews, Shapiro)nber.org, paper
Press
- Science (news, 22 Oct 2026): Across fields, AI finds solutions hiding in plain sightscience.org, press
- The Decoder: Open-source BootLoops harness supports AI models in precise scientific calculations (Oct 3)the-decoder.com, press
- Science (22 Oct): Across fields, AI finds solutions hiding in plain sight (Celina Zhao)science.org, press
Changes
- Added Science news coverage of 22 Oct (standfirst only; paywalled)
- Added the Science news feature of 22 Oct (abstract only; paywalled)
- Filed (Oct 3)